Matching image sets via adaptive multi convex hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

Tourism Destination Preferences: A Longitudinal Analysis of Consumer Decision Sets

There have only been a small number of applications of consumer decision set theory to holiday destination choice, and these studies have tended to rely on a single cross sectional snapshot of research participants’ stated preferences. Very little has been reported on the relationship between stated destination preferences and actual travel, or changes in decision set composition over time. The paper presents a rare longitudinal examination of destination decision sets, in the context of short break holidays by car in Queensland, Australia. Two questionnaires were administered, three months apart. The first identified destination preferences while the second examined actual travel and revisited destination preferences. In relation to the conference theme, there was very little change in consumer preferences towards the competitive set of destinations over the three month period. A key implication for the destination of interest, which, in an attempt to change market perceptions, launched a new brand campaign during the period of the project, is that a long term investment in a consistent brand message will be required to change market perceptions. The results go some way to support the proposition that the positioning of a destination into a consumer’s decision set represents a source of competitive advantage.

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.

Rough sets based reasoning and pattern mining for a two-stage information filtering system

This paper presents a novel two-stage information filtering model which combines the merits of term-based and pattern- based approaches to effectively filter sheer volume of information. In particular, the first filtering stage is supported by a novel rough analysis model which efficiently removes a large number of irrelevant documents, thereby addressing the overload problem. The second filtering stage is empowered by a semantically rich pattern taxonomy mining model which effectively fetches incoming documents according to the specific information needs of a user, thereby addressing the mismatch problem. The experiments have been conducted to compare the proposed two-stage filtering (T-SM) model with other possible "term-based + pattern-based" or "term-based + term-based" IF models. The results based on the RCV1 corpus show that the T-SM model significantly outperforms other types of "two-stage" IF models.

Exponentiated gradient algorithms for conditional random fields and max-margin Markov Networks

Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the log-linear or max-margin objective function; the dual in both the log-linear and max-margin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the max-margin case, O(1/ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for log-linear models only O(log(1/ε)) updates are required. For both the max-margin and log-linear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be efficiently applied to problems such as sequence learning or natural language parsing. We perform extensive evaluation of the algorithms, comparing them to L-BFGS and stochastic gradient descent for log-linear models, and to SVM-Struct for max-margin models. The algorithms are applied to a multi-class problem as well as to a more complex large-scale parsing task. In all these settings, the EG algorithms presented here outperform the other methods.

Optimal strategies and minimax lower bounds for online convex games

A number of learning problems can be cast as an Online Convex Game: on each round, a learner makes a prediction x from a convex set, the environment plays a loss function f, and the learner’s long-term goal is to minimize regret. Algorithms have been proposed by Zinkevich, when f is assumed to be convex, and Hazan et al., when f is assumed to be strongly convex, that have provably low regret. We consider these two settings and analyze such games from a minimax perspective, proving minimax strategies and lower bounds in each case. These results prove that the existing algorithms are essentially optimal.

The borders that law sets on entertainment

It is natural for those involved in entertainment to focus on the art. However, like any activity in even a free society, those involved in entertainment industries must operate within borders set by the law. This article examines the main areas of law that impact entertainment in an Australian context. It contrasts the position in relation to freedom of expression in Australia with that in the United States, which also promotes freedom of expression in a free society. It then briefly canvases the main limits on entertainment productions under Australian law.

Heterogeneity in auditory alarm sets makes them easier to learn

The primary objective of the experiments reported here was to demonstrate the effects of opening up the design envelope for auditory alarms on the ability of people to learn the meanings of a set of alarms. Two sets of alarms were tested, one already extant and one newly-designed set for the same set of functions, designed according to a rationale set out by the authors aimed at increasing the heterogeneity of the alarm set and incorporating some well-established principles of alarm design. For both sets of alarms, a similarity-rating experiment was followed by a learning experiment. The results showed that the newly-designed set was judged to be more internally dissimilar, and easier to learn, than the extant set. The design rationale outlined in the paper is useful for design purposes in a variety of practical domains and shows how alarm designers, even at a relatively late stage in the design process, can improve the efficacy of an alarm set.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.